Weil Institute members awarded $350k to combat fluid overload in pediatric heart surgery
New system will help save young lives by enhancing treatment of a deadly postoperative complication.
Contact:
Katelyn Murphy,
Marketing Communications Specialist, Weil Institute
mukately@med.umich.edu
ANN ARBOR, MI – Investigators from the University of Michigan Max Harry Weil Institute for Critical Care Research and Innovation and Michigan Medicine have teamed up to build an automated system that will optimize how care teams treat fluid overload, a dangerous complication associated with heart surgery.
Each year in the United States, approximately 40,000 children are born with a congenital heart defect--25% of whom will require surgery or other interventions within their first year (1). Cardiac procedures directly affect the heart’s pumping mechanisms, causing fluid that would otherwise be circulated throughout the body to build up to potentially dangerous levels. A standard method of reducing this fluid involves giving the patient diuretics to increase urine production. The process of titrating these medications is imprecise, however, and, in some cases, can even be detrimental.
"Thanks to [the Weil Institute Data Science team's] diligence and expertise, our model is poised to become the ‘smartest’ physiologic closed loop control system possible and generate substantial impact at the bedside."
Daniel Ehrmann, MD, MS
Assistant Professor, Pediatrics; Member, Weil Institute
Michigan Medicine
“In current practice, it’s difficult for clinicians to determine the correct dose,” said Dr. Daniel Ehrmann, Principal Investigator on the study, who also serves as Assistant Professor of Pediatrics and is a member of the Weil Institute. “The way diuretics are titrated varies significantly between clinicians and heart centers and can often lead to under- or over-diuresis, which causes patient harm.”
Supported by a three-year, $350,000 grant from the Gerber Foundation, Ehrmann and the team are developing a physiologic closed-loop control system capable of automatically adjusting a diuretic to achieve a precise amount of diuresis (increased excretion of urine) based on patient data. Similar to a household thermostat or the cruise control function in a car, a closed loop control system is a device that automatically regulates variables within a system so that a desired state can be maintained without human interaction. They have been studied across domains in critical care medicine in the management of bleeding, mechanical ventilation and sedation. However, unlike these systems, the team’s proposed device is powered by an advanced neural network trained on “fuzzy logic” to help it think more like a clinician. This allows it to more accurately adapt to changes in the recommended diuretic infusion and adjust its output accordingly.
“Fuzzy logic allows variables in our model to be interpreted along a spectrum, which dovetails nicely with how clinicians tend to think about data,” said Ehrmann. “For example, they might say a patient’s urine output is ‘a little low’ or ‘very low’ as opposed to just a binary ‘high’ or ‘low’. This is an advantage over other modeling approaches that oversimplify physiologic variables—and medical decision-making--to binaries defined by a discrete cutoff.”
Earlier this year, the team received funding for their project as one of two grand prize winners of the Frankel Cardiovascular Center’s Innovation Challenge. Now, with the additional support provided by the Gerber Foundation, they will be able to continue work on a prototype version of the system. They plan to build the system by first training the model on data from the electronic health record and will then deploy the system in a preclinical animal model of fluid overload in order to evaluate its safety and efficacy.
“The Weil Institute Data Science Core has been instrumental in this work,” said Ehrmann. “They have helped us curate a large multipronged dataset to capture the complexity of medical decision making in our modeling approach. Thanks to their diligence and expertise, our model is poised to become the ‘smartest’ physiologic closed loop control system possible and generate substantial impact at the bedside. With this system, we hope to bring about a transformation in care for infants and children with congenital heart disease.”
Project Team
Dan Ehrmann, M.D., M.S (Weil Institute, Pediatrics, Cardiology); Kayvan Najarian, Ph.D (Weil Institute, Computational Medicine and Bioinformatics); John Charpie, MD, Ph.D. (Weil Institute, Pediatrics, Cardiology); Gabe Owens, M.D. (Weil Institute, Pediatrics, Cardiology); Ranjit Aiyagari, M.D. (Pediatrics, Cardiology); Alvaro Rojas-Peña, M.D. (Weil Institute, Transplant Surgery); Emily Wittrup, M.S. (Weil Institute, Computational Medicine and Bioinformatics); Matt Hodgman, Ph.D (Computational Medicine and Bioinformatics)
About the Weil Institute, formerly MCIRCC
The team at the Max Harry Weil Institute for Critical Care Research and Innovation (formerly the Michigan Center for Integrative Research in Critical Care) is dedicated to pushing the leading edge of research to develop new technologies and novel therapies for the most critically ill and injured patients. Through a unique formula of innovation, integration and entrepreneurship that was first imagined by Weil, their multi-disciplinary teams of health providers, basic scientists, engineers, data scientists, commercialization coaches, donors and industry partners are taking a boundless approach to re-imagining every aspect of critical care medicine. For more information, visit weilinstitute.med.umich.edu.